Skip to main content

Lightning-fast LLM model introspection

Project description

rvnllm

rvnllm is a blazing-fast Python package for inspecting, diffing, and analyzing GGUF-based LLM model files.

Think ExifTool, but for large language models.

Features

  • Zero-copy GGUF model parsing
  • Tensor-level metadata inspection
  • Structural diffs between model files
  • Cross-platform wheels (Linux, macOS, Windows)

Installation

pip

pip install rvnllm

Build from source

git clone https://github.com/rvnllm/rvnllm.git
cd py/rvn_py
maturin build --release
pip install dist/*.whl

Usage example

import rvnllm

df = rvnllm.info("Llama-3-70B-Q4_0.gguf")
print(df.head())

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

rvn-0.1.7-cp310-cp310-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.34+ x86-64

rvn-0.1.7-cp38-abi3-manylinux_2_39_x86_64.whl (14.6 MB view details)

Uploaded CPython 3.8+manylinux: glibc 2.39+ x86-64

File details

Details for the file rvn-0.1.7-cp310-cp310-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvn-0.1.7-cp310-cp310-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 3cb04cbb5210f7c376cff0b5de2cd4f63265cf9474b317904f9b36bf7b78f3cb
MD5 2773ed5b9cc190d4fe035dd0cb3f22ed
BLAKE2b-256 baa414ee88857387f321afe40870a8778a7948648f9fd39f4cde87537bfdc15f

See more details on using hashes here.

File details

Details for the file rvn-0.1.7-cp38-abi3-manylinux_2_39_x86_64.whl.

File metadata

  • Download URL: rvn-0.1.7-cp38-abi3-manylinux_2_39_x86_64.whl
  • Upload date:
  • Size: 14.6 MB
  • Tags: CPython 3.8+, manylinux: glibc 2.39+ x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.12

File hashes

Hashes for rvn-0.1.7-cp38-abi3-manylinux_2_39_x86_64.whl
Algorithm Hash digest
SHA256 4063f8df0e05d7ba063307aa39bf568a8373eeaa52a5b91bfafc914bb629b556
MD5 474b22a573db5506f2fd04f8d83688e3
BLAKE2b-256 865fda80d2f8deb933255e66a4d5bbbd6fde903afc5249ebdd56d84eddb90885

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page